© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 2-GEMMASCOPE-RES-16K
    6. 1420
    Prev
    Next
    INDEX
    Explanations

    references to themes and plugins related to web development frameworks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aarrggbb
    -0.81
    MigrationBuilder
    -0.75
    GEBURTSDATUM
    -0.73
    principalTable
    -0.72
     resourceCulture
    -0.71
    expandindo
    -0.69
    randomUUID
    -0.69
    gameserver
    -0.68
     propOrder
    -0.68
    Autoritní
    -0.67
    POSITIVE LOGITS
     myſelf
    1.12
    ſelf
    1.09
     Houſe
    1.04
     Jefus
    1.04
    ſelves
    1.03
     Majefty
    0.99
     himſelf
    0.97
     Monfieur
    0.93
     itſelf
    0.93
     iſt
    0.90
    Activations Density 12.557%

    No Known Activations